INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     porad
    0.83
     nightmares
    0.80
     lockers
    0.78
     dearest
    0.77
     teenage
    0.76
     adolescente
    0.75
     diets
    0.75
     daily
    0.73
     adolescentes
    0.73
     teens
    0.72
    POSITIVE LOGITS
     fully
    0.99
    Fully
    0.86
     sixty
    0.85
     full
    0.85
     well
    0.84
     Fully
    0.82
    full
    0.82
     fullness
    0.82
    Well
    0.81
     completed
    0.77
    Act Density 0.006%

    No Known Activations